A method of generating audio assets, comprising the steps of: receiving a plurality of input audio assets, converting each input audio asset into an input graphical representation, generating an input multi-channel image by stacking each input graphical representation in a separate channel of the image, feeding the input multi-channel image into a generative model to train the generative model and generate one or more output multi-channel images, each output multi-channel image comprising an output graphical representation, extracting the output graphical representations from each output multi-channel image and converting each output graphical representation into an output audio asset.

A method of generating audio assets, comprising the steps of: receiving an input multi-layered audio asset comprising a plurality of audio layers, generating an input multi-channel image, wherein each channel of the input multi-channel image comprises an input image representative of one of the audio layers, training a generative model on the input multi-channel image and implementing the trained generative model to generate an output multi-channel image, wherein each channel of the output multi-channel image comprises an output image representative of an output audio layer, and generating an output multi-layered audio asset based on a combination of output audio layers derived from the output images.

A method of generating audio assets, comprising the steps of: receiving an input audio asset having a first duration, generating an input image representative of the input audio asset, training a generative model on the input image and implementing the trained generative model to generate an output image representative of an output audio asset having a second duration different to the first duration, and generating the output audio asset based on the output image.

Disclosed herein are systems and methods for presenting an audio signal associated with presentation of a virtual object colliding with a surface. The virtual object and the surface may be associated with a mixed reality environment. Generation of the audio signal may be based on at least one of an audio stream from a microphone and a video stream form a sensor. In some embodiments, the collision between the virtual object and the surface is associated with a footstep on the surface.

Disclosed herein are systems and methods for presenting an audio signal associated with presentation of a virtual object colliding with a surface. The virtual object and the surface may be associated with a mixed reality environment. Generation of the audio signal may be based on at least one of an audio stream from a microphone and a video stream form a sensor. In some embodiments, the collision between the virtual object and the surface is associated with a footstep on the surface.

Disclosed are a method and apparatus for controlling an inverter of an eco-friendly vehicle, which may generate noise outside of a frequency band audible to infants in a protection mode. The control method includes calculating a current noise frequency, determining whether the current noise frequency is higher than a target noise frequency, and changing a current inverter switching frequency based on the real-time motor rotation frequency to generate noise corresponding to the target noise frequency when the current noise frequency is lower than the target noise frequency. Accordingly, it may be possible to prevent noise generated when the eco-friendly vehicle is driven from affecting the sense of hearing of an infant in the vehicle, whose audible frequency band is higher than that of an adult, thereby preventing hearing loss of the infant.

Disclosed are a method and apparatus for controlling an inverter of an eco-friendly vehicle, which may generate noise outside of a frequency band audible to infants in a protection mode. The control method includes calculating a current noise frequency, determining whether the current noise frequency is higher than a target noise frequency, and changing a current inverter switching frequency based on the real-time motor rotation frequency to generate noise corresponding to the target noise frequency when the current noise frequency is lower than the target noise frequency. Accordingly, it may be possible to prevent noise generated when the eco-friendly vehicle is driven from affecting the sense of hearing of an infant in the vehicle, whose audible frequency band is higher than that of an adult, thereby preventing hearing loss of the infant.

An ultrasonic speaker comprises a case that has an opened top surface and includes a plurality of protrusions protruding inward on an inner side surface of the case, a piezoelectric element fixed to a bottom surface in the case, and a substrate that is inserted in the case and placed on upper surfaces of the plurality of protrusions.

Systems and methods to augment audio output in an electric vehicle (EV) include obtaining inputs from one or more sensors. The inputs include information about the EV and about one or more persons outside the EV. A current scenario is defined based on the inputs. Whether the current scenario matches a predefined scenario among a set of predefined scenarios is determined, and augmented audio output is produced according to the predefined scenario.

Systems and methods to augment audio output in an electric vehicle (EV) include obtaining inputs from one or more sensors. The inputs include information about the EV and about one or more persons outside the EV. A current scenario is defined based on the inputs. Whether the current scenario matches a predefined scenario among a set of predefined scenarios is determined, and augmented audio output is produced according to the predefined scenario.